Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Classification and quantification of microplastic (< 100 µm) using FPA-FTIR imaging system and machine learning.

In Analytical chemistry

Microplastics are defined as microscopic plastic particles in the range from few µm and up to 5 mm. These small particles are classified as primary microplastic when they are manufactured in this size range, whereas secondary microplastics arise from the fragmentation of larger objects. Microplastics are a widespread emerging pollutant and investigations are underway to determine potential harmfulness to biota and human health. However, progress is hindered by the lack of suitable analytical methods for rapid, routine and unbiased measurements. This work aims to develop an automated analytical method for the characterization of small microplastic (< 100 µm) using micro Fourier Transform Infrared (µ-FTIR) hyper-spectral imaging and machine learning tools. Partial least squares discriminant analysis (PLS-DA) and soft independent modelling of class analogy (SIMCA) models were evaluated, applying different data pre-processing strategies for classification of nine of the most common polymers produced worldwide. The hyperspectral images were also analyzed to quantify particle abundance and size automatically. PLS-DA presented a better analytical performance in comparison with SIMCA models with higher sensitivity, sensibility and lower misclassification error. PLS-DA was less sensitive to edge effects on spectra and poorly focused regions of particles. The approach was tested on a seabed sediment sample (Roskilde Fjord, Denmark) to demonstrate the method efficiency. The proposed method offers an efficient automated approach for microplastic polymer characterization, abundance numeration and size distribution with substantial benefits for methods standardization.

da Silva Vitor Hugo, Murphy Fionn, Amigo Jose Manuel, Stedmon Colin Andrew, Strand Jakob

2020-Sep-18

Pathology Pathology

A Single-Cell RNA Expression Map of Human Coronavirus Entry Factors.

In Cell reports ; h5-index 119.0

To predict the tropism of human coronaviruses, we profile 28 SARS-CoV-2 and coronavirus-associated receptors and factors (SCARFs) using single-cell transcriptomics across various healthy human tissues. SCARFs include cellular factors both facilitating and restricting viral entry. Intestinal goblet cells, enterocytes, and kidney proximal tubule cells appear highly permissive to SARS-CoV-2, consistent with clinical data. Our analysis also predicts non-canonical entry paths for lung and brain infections. Spermatogonial cells and prostate endocrine cells also appear to be permissive to SARS-CoV-2 infection, suggesting male-specific vulnerabilities. Both pro- and anti-viral factors are highly expressed within the nasal epithelium, with potential age-dependent variation, predicting an important battleground for coronavirus infection. Our analysis also suggests that early embryonic and placental development are at moderate risk of infection. Lastly, SCARF expression appears broadly conserved across a subset of primate organs examined. Our study establishes a resource for investigations of coronavirus biology and pathology.

Singh Manvendra, Bansal Vikas, Feschotte Cédric

2020-Sep-03

COVID-19, SARS-CoV-2, coronaviruses, restriction factors, scRNA-seq, viral receptors

General General

A deep learning network-assisted Bladder Tumor Recognition under Cystoscopy Based on Caffe Deep Learning Framework and EasyDL Platform.

In The international journal of medical robotics + computer assisted surgery : MRCAS

BACKGROUND : Cystoscopy plays an important role in the diagnosis of bladder tumors. As a typical representative of the deep learning algorithm, the convolutional neural network has shown great advantages in the field of image recognition and segmentation.

METHODS : 1002 photographs of normal bladder tissue and 734 photos of bladder tumors under cystoscopy were taken from 175 patients. Caffe deep learning framework and EasyDL platform were used to structure and train the model. The trained model from the EasyDL platform was deployed on a mobile phone.

RESULTS : The accuracy rate of the neural network to recognise the bladder cancer based on Caffe framework was 82.9%, and the data on the EasyDL platform was 96.9%. The model came from EasyDL platform could discern bladder cancer accurately on the phone and website.

CONCLUSION : The deep learning network could recognise the bladder cancer accurately. Deploy that model on the mobile phone was useful for clinical use. This article is protected by copyright. All rights reserved.

Du Yang, Yang Rui, Chen Zhiyuan, Wang Lei, Weng Xiaodong, Liu Xiuheng

2020-Sep-18

Caffe framework, EasyDL framework, bladder cancer, convolution neural network, deploy, recognition

General General

Automatic detection of colorectal neoplasias in wireless colon capsule endoscopic images using a deep convolutional neural network.

In Endoscopy ; h5-index 58.0

BACKGROUND AND AIMS : Although colorectal neoplasias are the most common abnormalities found in colon capsule endoscopy (CCE), no computer-aided detection method is yet available. We developed an artificial intelligence (AI) system that uses deep learning to automatically detect such lesions in CCE images.

METHODS : We trained a deep convolutional neural network system based on a Single Shot Multibox Detector using 15,933 CCE images of colorectal neoplasias such as polyps and cancers. We assessed performance by calculating areas under the receiver operating characteristic curves and sensitivities, specificities, and accuracies using an independent test set of 4,784 images including 1,850 images of colorectal neoplasias and 2,934 normal colon images.

RESULTS : The area under the curve for detection by the AI model of colorectal neoplasias was 0.902. The sensitivity, specificity, and accuracy were 79.0%, 87.0%, and 83.9%, respectively, at a probability cutoff of 0.348.

CONCLUSIONS : We developed and validated a new AI-based system that automatically detects colorectal neoplasias in CCE images.

Yamada Atsuo, Niikura Ryota, Otani Keita, Aoki Tomonori, Koike Kazuhiko

2020-Sep-18

General General

The intestinal microbiome is a co-determinant of the postprandial plasma glucose response.

In PloS one ; h5-index 176.0

Elevated postprandial plasma glucose is a risk factor for development of type 2 diabetes and cardiovascular disease. We hypothesized that the inter-individual postprandial plasma glucose response varies partly depending on the intestinal microbiome composition and function. We analyzed data from Danish adults (n = 106), who were self-reported healthy and attended the baseline visit of two previously reported randomized controlled cross-over trials within the Gut, Grain and Greens project. Plasma glucose concentrations at five time points were measured before and during three hours after a standardized breakfast. Based on these data, we devised machine learning algorithms integrating bio-clinical, as well as shotgun-sequencing-derived taxa and functional potentials of the intestinal microbiome to predict individual postprandial glucose excursions. In this post hoc study, we found microbial and clinical features, which predicted up to 48% of the inter-individual variance of postprandial plasma glucose responses (Pearson correlation coefficient of measured vs. predicted values, R = 0.69, 95% CI: 0.45 to 0.84, p<0.001). The features were age, fasting serum triglycerides, systolic blood pressure, BMI, fasting total serum cholesterol, abundance of Bifidobacterium genus, richness of metagenomics species and abundance of a metagenomic species annotated to Clostridiales at order level. A model based only on microbial features predicted up to 14% of the variance in postprandial plasma glucose excursions (R = 0.37, 95% CI: 0.02 to 0.64, p = 0.04). Adding fasting glycaemic measures to the model including microbial and bio-clinical features increased the predictive power to R = 0.78 (95% CI: 0.59 to 0.89, p<0.001), explaining more than 60% of the inter-individual variance of postprandial plasma glucose concentrations. The outcome of the study points to a potential role of the taxa and functional potentials of the intestinal microbiome. If validated in larger studies our findings may be included in future algorithms attempting to develop personalized nutrition, especially for prediction of individual blood glucose excursions in dys-glycaemic individuals.

Søndertoft Nadja B, Vogt Josef K, Arumugam Manimozhiyan, Kristensen Mette, Gøbel Rikke J, Fan Yong, Lyu Liwei, Bahl Martin I, Eriksen Carsten, Ängquist Lars, Frøkiær Hanne, Hansen Tue H, Brix Susanne, Nielsen H Bjørn, Hansen Torben, Vestergaard Henrik, Gupta Ramneek, Licht Tine R, Lauritzen Lotte, Pedersen Oluf

2020

General General

Graph Convolutional Networks-Based Noisy Data Imputation in Electronic Health Record.

In Critical care medicine ; h5-index 87.0

OBJECTIVES : A deep learning-based early warning system is proposed to predict sepsis prior to its onset.

DESIGN : A novel algorithm was devised to detect sepsis 6 hours prior to its onset based on electronic medical records.

SETTING : Retrospective cohorts from three separate hospitals are used in this study. Sepsis onset was defined based on Sepsis-3. Algorithms are evaluated based on the score function used in the Physionet Challenge 2019.

PATIENTS : Over 60,000 ICU patients with 40 clinical variables (vital signs, laboratory results) for each hour of a patient's ICU stay were used.

INTERVENTIONS : None.

MEASUREMENTS AND MAIN RESULTS : The proposed algorithm predicted the onset of sepsis in the preceding n hours (where n = 4, 6, 8, or 12). Furthermore, the proposed method compared how many sepsis patients can be predicted in a short time with other methods. To interpret a given result in a clinical perspective, the relationship between input variables and the probability of the proposed method were presented. The proposed method achieved superior results (area under the receiver operating characteristic curve, area under the precision-recall curve, and score) and predicted more sepsis patients in advance. In official phase, the proposed method showed the utility score of -0.101, area under the receiver operating characteristic curve 0.782, area under the precision-recall curve 0.041, accuracy 0.786, and F-measure 0.046.

CONCLUSIONS : Using Physionet Challenge 2019, the proposed method can accurately and early predict the onset of sepsis. The proposed method can be a practical early warning system in the environment of real hospitals.

Lee Byeong Tak, Kwon O-Yeon, Park Hyunho, Cho Kyung-Jae, Kwon Joon-Myoung, Lee Yeha

2020-Sep-18